Sequential fusion estimation for multisensor systems with non-Gaussian noises  

作　　者：Liping YAN Chenying DI Q.M.Jonathan WU Yuanqing XIA 

机构地区：[1]Key Laboratory of Intelligent Control and Decision of Complex Systems,School of Automation,Beijing Institute of Technology,Beijing 100081,China [2]Department of Electrical and Computer Engineering,University of Windsor,Windsor N9B3P4,Canada

出　　处：《Science China(Information Sciences)》2020年第12期149-161,共13页中国科学（信息科学）（英文版）

基　　金：supported by Beijing Natural Science Foundation(Grant No.4202071)。

摘　　要：The sequential fusion estimation for multisensor systems disturbed by non-Gaussian but heavytailed noises is studied in this paper.Based on multivariate t-distribution and the approximate t-filter,the sequential fusion algorithm is presented.The performance of the proposed algorithm is analyzed and compared with the t-filter-based centralized batch fusion and the Gaussian Kalman filter-based optimal centralized fusion.Theoretical analysis and exhaustive experimental analysis show that the proposed algorithm is effective.As the generalization of the classical Gaussian Kalman filter-based optimal sequential fusion algorithm,the presented algorithm is shown to be superior to the Gaussian Kalman filter-based optimal centralized batch fusion and the optimal sequential fusion in estimation of dynamic systems with non-Gaussian noises.

关 键 词：state estimation sequential fusion non-Gaussian disturbance heavy-tailed noise multivariate t-distribution 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]